Merge branch 'sched/urgent' into sched/core

Merge in the latest fixes before applying a dependent patch.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 19 insertions, 29 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 725aa067ad63..5ac63c9a995a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -978,13 +978,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		rq->skip_clock_update = 1;
 }
 
-static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
-
-void register_task_migration_notifier(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&task_migration_notifier, n);
-}
-
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -1015,18 +1008,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
-		struct task_migration_notifier tmn;
-
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
-
-		tmn.task = p;
-		tmn.from_cpu = task_cpu(p);
-		tmn.to_cpu = new_cpu;
-
-		atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ace34f95e200..99947919e30b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -551,10 +551,7 @@ static void cputime_adjust(struct task_cputime *curr,
 			   struct cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, stime, utime, total;
-
-	stime = curr->stime;
-	total = stime + curr->utime;
+	cputime_t rtime, stime, utime;
 
 	/*
 	 * Tick based cputime accounting depend on random scheduling
@@ -576,13 +573,19 @@ static void cputime_adjust(struct task_cputime *curr,
 	if (prev->stime + prev->utime >= rtime)
 		goto out;
 
-	if (total) {
+	stime = curr->stime;
+	utime = curr->utime;
+
+	if (utime == 0) {
+		stime = rtime;
+	} else if (stime == 0) {
+		utime = rtime;
+	} else {
+		cputime_t total = stime + utime;
+
 		stime = scale_stime((__force u64)stime,
 				    (__force u64)rtime, (__force u64)total);
 		utime = rtime - stime;
-	} else {
-		stime = rtime;
-		utime = 0;
 	}
 
 	/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 51c5c3ee77e3..71c6ef58bbb9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4245,7 +4245,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se) {
-		cfs_rq->h_load = rq->avg.load_avg_contrib;
+		cfs_rq->h_load = cfs_rq->runnable_load_avg;
 		cfs_rq->last_h_load_update = now;
 	}
 
@@ -4813,8 +4813,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 		(busiest->load_per_task * SCHED_POWER_SCALE) /
 		busiest->group_power;
 
-	if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
-	    (scaled_busy_load_per_task * imbn)) {
+	if (busiest->avg_load + scaled_busy_load_per_task >=
+	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
 		env->imbalance = busiest->load_per_task;
 		return;
 	}
@@ -4886,7 +4886,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (busiest->avg_load < sds->avg_load) {
+	if (busiest->avg_load <= sds->avg_load ||
+	    local->avg_load >= sds->avg_load) {
 		env->imbalance = 0;
 		return fix_small_imbalance(env, sds);
 	}
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 5aef494fc8b4..c7edee71bce8 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -104,8 +104,9 @@ static inline void sched_info_queued(struct task_struct *t)
 }
 
 /*
- * Called when a process ceases being the active-running process, either
- * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ * Called when a process ceases being the active-running process involuntarily
+ * due, typically, to expiring its time slice (this may also be called when
+ * switching to the idle task).  Now we can calculate how long we ran.
  * Also, if the process is still in the TASK_RUNNING state, call
  * sched_info_queued() to mark that it has now again started waiting on
  * the runqueue.